Inertia-1: An Open Exploration to a Unified Motion Foundation Model

# Inertia-1 — A Universal Motion Model Source: [https://yang-ai-lab.github.io/Inertia-1/](https://yang-ai-lab.github.io/Inertia-1/) The big idea ## Towards one general motion model Motion is universal — but the models built for it weren't\. Inertia\-1 brings the whole landscape under one roof\. 01A fragmented fieldDatasets disagree on the basics — sampling rate, window length, sensor modality, body placement, even signal format — and every task gets its own bespoke model\. Findings rarely carry from one setup to the next\. 02One unified explorationInertia\-1 studies the full lifecycle of motion models — data, sensing, objectives, and scale — inside a single, controlled space instead of isolated one\-offs\. 03A general representationThe payoff: one representation that adapts across placements, devices, and tasks — the same backbone, working far beyond the setting it was trained on\. HeadChestBackArmWristHandHipThighKneeShinAnkleAccelerometerGyroscopeMagnetometerTriaxialENMO0\.2 Hz1 Hz5 Hz20 Hz10 s window30 s window60 s window2 hr windowFrequency domainTime domainActivity recognitionGait detectionLongitudinal healthHeadChestBackArmWristHandHipThighKneeShinAnkleAccelerometerGyroscopeMagnetometerTriaxialENMO0\.2 Hz1 Hz5 Hz20 Hz10 s window30 s window60 s window2 hr windowFrequency domainTime domainActivity recognitionGait detectionLongitudinal health What we found Beyond benchmarks, Inertia\-1 surfaces the choices that decide whether a motion model actually works in the real world\. ## Learn it on the wrist\. Use it anywhere on the body\.  Pretrain once on the wrist, then point the model anywhere\. It holds up on body placements — and even sensor types like gyroscope and magnetometer — that it never saw during training\. No retraining for each new spot on the body\.  Wrist accelerometerOther sensors · gyro, magOther placements **Fused representation***higher accuracy · cleaner motion clusters* ## Add more streams\. Get more signal\.  Stack on more streams — extra placements, gyroscope, magnetometer — and the learned representation gets both more accurate and cleaner, with activities separating into tighter clusters\. The streams are complementary: each one catches something the others miss\. Also worth knowing ## Sensing design is a first\-order choice How you capture motion shapes what a model can do with it\. A few practical rules of thumb from the study\. - Pretrained models stay strong even at a low 1 Hz for activity recognition; finer\-grained health signals benefit from higher sampling rates\. - 30–60 second windows hit the sweet spot across most tasks — long enough to capture context, short enough to stay sharp\. - Full triaxial input consistently beats collapsed vector\-magnitude summaries — the extra axes carry signal worth keeping\. - Time\-domain modeling preserves gait and health cues better than frequency\-domain reconstruction\. How it works ## One pipeline, from raw signal to real\-world insight The general representation comes together in three clean steps\. 01 Pretrain at scale Learn from planetary\-scale accelerometry — over 18 million hours across global cohorts — with self\-supervision, no labels required\. 02 Transfer across settings Adapt the same representation to new placements, devices, and sampling rates with light tuning — or none at all\. 03 Deploy across tasks Power activity, mobility, and health applications from one backbone — from fitness tracking to clinical screening\. Capabilities ## From movement to meaning The same representation spans the full spectrum of motion understanding\. ## One general model for human motion Inertia\-1 is a first step toward a unified motion foundation model — and an open invitation to collaborators with motion data, new tasks, or a shared interest in where the field is headed\.